© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90588
    Prev
    Next
    INDEX
    Explanations

    names and movie titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     argued
    -0.89
     pasi
    -0.88
     mani
    -0.84
     calab
    -0.79
    环保
    -0.78
     persi
    -0.77
     poft
    -0.77
    Posi
    -0.76
    棠
    -0.74
     arguing
    -0.74
    POSITIVE LOGITS
    ющи
    0.85
    ##############
    0.85
    newList
    0.82
    țional
    0.81
     mitad
    0.79
     Ý
    0.79
    зовый
    0.77
    atonin
    0.76
     Unser
    0.76
    ">"
    0.75
    Activations Density 1.398%

    No Known Activations